发表机构
Purdue University（普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对跨域3D类增量学习中存在的性能差异问题，提出无示例方法PolyMem，通过建模特征分布高阶统计量缓解差异并提升跨域性能。
AI 中文摘要
3D感知在自动驾驶、机器人技术以及AR/VR等实际应用中发挥着关键作用。在实际场景中，3D感知模型需要持续适应新出现的3D物体类别，这使得类增量学习（CIL）尤为重要。然而，与2D图像不同，3D点云具有固有的异质性：同一类别的物体不仅可能来自干净的CAD域，还可能来自不同质量的RGB-D相机扫描、视频重建甚至损坏的观测数据。我们发现，这种异质性会引入灾难性遗忘之外的新挑战：不同域之间的性能下降程度可能存在显著差异，我们将这一现象称为性能差异。为研究该问题，我们建立了包含来自异质域点云类别的Domain3D-CIL训练与评估协议。我们进一步将多种主流CIL方法适配到3D模态，结果表明该性能差异在这些基线方法中持续存在。为缓解这一问题，我们提出了PolyMem，这是一种无示例的方法，可隐式建模特征分布的丰富高阶统计量以增强跨域鲁棒性。实验表明，我们的方法能有效缓解性能差异，同时提升模型在各域的性能。代码将在论文接收后公开。
英文摘要
3D perception plays a crucial role in real-world applications such as autonomous driving, robotics, and AR/VR. In practical scenarios, 3D perception models need to continually adapt to newly emerging 3D object categories, making class-incremental learning (CIL) particularly important. However, unlike 2D images, 3D point clouds are inherently heterogeneous: objects from the same class may not only come from the clean CAD domain, but also from RGB-D camera scans of varying quality, video reconstructions, or even corrupted observations. We discover that such heterogeneity introduces a new challenge beyond catastrophic forgetting: the degree of performance degradation can vary substantially across domains, a phenomenon we term performance discrepancy. To investigate this problem, we establish the Domain3D-CIL training and evaluation protocol, which contains point cloud categories from heterogeneous domains. We further adapt a wide range of mainstream CIL methods to the 3D modality. The results demonstrate that this performance discrepancy consistently appears across these baselines. To mitigate this issue, we introduce PolyMem, an exemplar-free approach that implicitly models rich high-order statistics of the feature distribution to enhance cross-domain robustness. Experiments demonstrate that our method effectively alleviates the performance discrepancy while improving the model's performance across domains. Code will be made publicly available upon acceptance.
Comments29 pages
